© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 3644
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds, oxidation, farming equipment, animal names, and potentially names or places starting with "Ox."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "oxidation" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATURES
    -0.74
     permission
    -0.69
    WAYS
    -0.67
    ————————
    -0.64
     Apprentice
    -0.63
    ------------------------------------------------
    -0.62
     iT
    -0.62
     Garrison
    -0.62
     Archangel
    -0.61
    ATURE
    -0.61
    POSITIVE LOGITS
    fam
    1.10
    nard
    1.04
    idation
    1.02
    ilon
    0.99
     Ox
    0.95
    Ox
    0.93
    iola
    0.92
    bridge
    0.91
    rex
    0.91
    yssey
    0.90
    Activations Density 0.008%

    No Known Activations